Related papers: New Intent Discovery with Attracting and Dispersin…

Intent detection, a critical component in task-oriented dialogue (TOD) systems, faces significant challenges in adapting to the rapid influx of integrable tools with complex interrelationships. Existing approaches, such as zero-shot…

We tackle the problem of novel class discovery and localization (NCDL). In this setting, we assume a source dataset with supervision for only some object classes. Instances of other classes need to be discovered, classified, and localized…

We propose a novel inherently interpretable machine learning method that bases decisions on few relevant examples that we call prototypes. Our method, ProtoAttend, can be integrated into a wide range of neural network architectures…

As AI agents are increasingly used in the real open world with unknowns or novelties, they need the ability to (1) recognize objects that (a) they have learned before and (b) detect items that they have never seen or learned, and (2) learn…

Existing prompt learning methods have shown certain capabilities in Out-of-Distribution (OOD) detection, but the lack of OOD images in the target dataset in their training can lead to mismatches between OOD images and In-Distribution (ID)…

In real-world graph data, distribution shifts can manifest in various ways, such as the emergence of new categories and changes in the relative proportions of existing categories. It is often important to detect nodes of novel categories…

Anomaly detection plays a critical role in Autonomous Vehicles (AVs) by identifying unusual behaviors through perception systems that could compromise safety and lead to hazardous situations. Current approaches, which often rely on…

Node classification on graphs is of great importance in many applications. Due to the limited labeling capability and evolution in real-world open scenarios, novel classes can emerge on unlabeled testing nodes. However, little attention has…

Active learning (AL) strategies aim to train high-performance models with minimal labeling efforts, only selecting the most informative instances for annotation. Current approaches to evaluating data informativeness predominantly focus on…

Slot and intent detection (SID) is a classic natural language understanding task. Despite this, research has only more recently begun focusing on SID for dialectal and colloquial varieties. Many approaches for low-resource scenarios have…

Open intent classification is a challenging task in dialogue systems. On the one hand, it should ensure the quality of known intent identification. On the other hand, it needs to detect the open (unknown) intent without prior knowledge.…

We propose a new active learning (AL) method for text classification with convolutional neural networks (CNNs). In AL, one selects the instances to be manually labeled with the aim of maximizing model performance with minimal effort. Neural…

Advanced persistent threats (APTs) pose significant challenges for organizations, leading to data breaches, financial losses, and reputational damage. Existing provenance-based approaches for APT detection often struggle with high false…

Imitation learning aims to learn a policy from observing expert demonstrations without access to reward signals from environments. Generative adversarial imitation learning (GAIL) formulates imitation learning as adversarial learning,…

Unsupervised visible-infrared person re-identification (USVI-ReID) aims to match specified people in infrared images to visible images without annotations, and vice versa. USVI-ReID is a challenging yet under-explored task. Most existing…

Network attacks have became increasingly more sophisticated and stealthy due to the advances in technologies and the growing sophistication of attackers. Advanced Persistent Threats (APTs) are a type of attack that implement a wide range of…

Despite deep convolutional neural networks' great success in object classification, it suffers from severe generalization performance drop under occlusion due to the inconsistency between training and testing data. Because of the large…

Accurately modeling users' evolving preferences from sequential interactions remains a central challenge in recommender systems. Recent studies emphasize the importance of capturing multiple latent intents underlying user behaviors.…

Class incremental learning (CIL) is a challenging setting of continual learning, which learns a series of tasks sequentially. Each task consists of a set of unique classes. The key feature of CIL is that no task identifier (or task-id) is…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources to improve factual accuracy and verifiability. However, this reliance introduces new attack surfaces within…